Archive
LLM Infrastructure

Triton's Serving Cousin

Archive
Very Easy
50pts0 solves
NVIDIA's general-purpose model serving daemon — predates the LLM era, serves TF/PyTorch/ONNX models with dynamic batching — is called what?
Show hint
Three words, the first is a Greek sea-god.

Archive — no submissions accepted

This challenge is preserved for reference. Play live challenges at /challenges.